Code for Video Retrieval

X-PLUG / mPLUG-Owl

mPLUG-Owl: The Powerful Multi-modal Large Language Model Family

https://www.modelscope.cn/studios/damo/mPLUG-Owl

MIT License

2.25k stars 171 forks source link

Code for Video Retrieval #121

Closed Hritikbansal closed 1 year ago

Hritikbansal commented 1 year ago

Hi @MAGAer13 @LukeForeverYoung @xuguohai ,

Can you point me to the video-text retrieval code in the repo? If there is no direct code for it, can you point me to the exact text and video embeddings that can be used for calculating the text-video similarity?

This is a followup to an issue in the mPLUG-2 repo (https://github.com/X-PLUG/mPLUG-2/issues/5).

MAGAer13 commented 1 year ago

Please refer to https://github.com/X-PLUG/mPLUG/blob/main/models/model_retrieval_mplug.py which is similar for video-text retrieval.